Predicting All-Cause Hospital Readmissions from Medical Claims Data of Hospitalised Patients

TL;DR

This study applies machine learning models to medical claims data to predict hospital readmissions, aiming to improve healthcare quality and reduce costs by identifying key risk factors.

Contribution

It introduces a methodology combining PCA with machine learning models to effectively predict all-cause readmissions from high-dimensional claims data.

Findings

Random Forest achieved the highest AUC performance

PCA effectively reduced data dimensionality for modeling

Models can identify key factors influencing readmissions

Abstract

Reducing preventable hospital readmissions is a national priority for payers, providers, and policymakers seeking to improve health care and lower costs. The rate of readmission is being used as a benchmark to determine the quality of healthcare provided by the hospitals. In thisproject, we have used machine learning techniques like Logistic Regression, Random Forest and Support Vector Machines to analyze the health claims data and identify demographic and medical factors that play a crucial role in predicting all-cause readmissions. As the health claims data is high dimensional, we have used Principal Component Analysis as a dimension reduction technique and used the results for building regression models. We compared and evaluated these models based on the Area Under Curve (AUC) metric. Random Forest model gave the highest performance followed by Logistic Regression and Support Vector Machine models. These models can be used to identify the crucial factors causing readmissions and help identify patients to focus on to reduce the chances of readmission, ultimately bringing down the cost and increasing the quality of healthcare provided to the patients.